© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17851
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or businesses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, primarily focusing on "Nob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.80
     Nadu
    -0.78
    ocker
    -0.74
     Zeit
    -0.71
    ization
    -0.68
    EngineDebug
    -0.67
    Angelo
    -0.67
    é»Ĵ
    -0.67
    xual
    -0.67
     Gazette
    -0.67
    POSITIVE LOGITS
    leness
    1.05
    uilt
    0.96
    lich
    0.95
    rants
    0.95
    ility
    0.95
    odies
    0.95
    aido
    0.94
    bey
    0.93
    rig
    0.89
    lisher
    0.87
    Activations Density 0.017%

    No Known Activations